US10453270B2 - Scalable real-time face beautification of video images - Google Patents

Scalable real-time face beautification of video images Download PDF

Info

Publication number
US10453270B2
US10453270B2 US15/127,785 US201515127785A US10453270B2 US 10453270 B2 US10453270 B2 US 10453270B2 US 201515127785 A US201515127785 A US 201515127785A US 10453270 B2 US10453270 B2 US 10453270B2
Authority
US
United States
Prior art keywords
beautification
facial
skin tone
face
skin
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
US15/127,785
Other languages
English (en)
Other versions
US20180174370A1 (en
Inventor
Ke Chen
Zhipin Deng
Xiaoxia Cai
Chen Wang
Ya-Ti Peng
Yi-Jen Chiu
Lidong Xu
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tahoe Research Ltd
Original Assignee
Intel Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Intel Corp filed Critical Intel Corp
Publication of US20180174370A1 publication Critical patent/US20180174370A1/en
Assigned to INTEL CORPORATION reassignment INTEL CORPORATION ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: PENG, YA-TI, CHIU, YI-JEN, CHEN, KE, CAI, XIAOXIA, DENG, Zhipin, XU, LIDONG, WANG, CHEN
Application granted granted Critical
Publication of US10453270B2 publication Critical patent/US10453270B2/en
Assigned to TAHOE RESEARCH, LTD. reassignment TAHOE RESEARCH, LTD. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: INTEL CORPORATION
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/70—Denoising; Smoothing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T19/00—Manipulating 3D models or images for computer graphics
    • G06T19/20—Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
    • G06K9/00228—
    • G06K9/00268—
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T15/00—3D [Three Dimensional] image rendering
    • G06T15/005—General purpose rendering architectures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/90—Dynamic range modification of images or parts thereof
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168—Feature extraction; Face representation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10024—Color image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20024—Filtering details
    • G06T2207/20028—Bilateral filtering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person
    • G06T2207/30201—Face

Definitions

  • Video sharing and conferencing has been increasingly used with the pervasive usage of smart phone.
  • many of the existing apps for smart phones are designed for off-line image processing or might not work with out limited features in a video mode.
  • FIG. 1 is an illustrative diagram of an example face beautification (FB) video augmentation pipe
  • FIG. 2 is an illustrative diagram of an example flow diagram of face based video augmentation on a graphics processor
  • FIG. 3 is an illustrative diagram of an example face beautification (FB) video augmentation scheme implemented on a mobile platform GPU;
  • FB face beautification
  • FIG. 4 is an illustrative diagram of an example flexible virtual GPU configuration implemented on a sever platform GPU
  • FIG. 5 is an illustrative diagram of an example skin smooth filter flow chart
  • FIG. 6 is an illustrative diagram of an example foundation color flow chart
  • FIG. 7 is an illustrative diagram of an example skin tone enhancement flow chart
  • FIG. 8 is an illustrative diagram of an example face brightening flow chart
  • FIG. 9 is an illustrative diagram of an example face whitening flow chart
  • FIG. 10 is an illustrative diagram of an example red lip filter flow chart
  • FIG. 11 is an illustrative diagram of example parameters used in warping
  • FIG. 12 is an illustrative diagram of an example big eyes filter flow chart
  • FIG. 13 is an illustrative diagram of an example slim face filter flow chart
  • FIG. 14 provides an illustrative diagram of an example face beautification process
  • FIG. 15 provides an illustrative diagram of an example video augmentation pipe and face beautification process in operation
  • FIG. 16 is an illustrative diagram of an example video coding system
  • FIG. 17 is an illustrative diagram of an example system.
  • FIG. 18 is an illustrative diagram of an example system, all arranged in accordance with at least some implementations of the present disclosure.
  • a machine-readable medium may include any medium and/or mechanism for storing or transmitting information in a form readable by a machine (e.g., a computing device).
  • a machine-readable medium may include read only memory (ROM); random access memory (RAM); magnetic disk storage media; optical storage media; flash memory devices; electrical, optical, acoustical or other forms of propagated signals (e.g., carrier waves, infrared signals, digital signals, etc.), and others.
  • references in the specification to “one implementation”, “an implementation”, “an example implementation”, etc., indicate that the implementation described may include a particular feature, structure, or characteristic, but every implementation may not necessarily include the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same implementation. Further, when a particular feature, structure, or characteristic is described in connection with an implementation, it is submitted that it is within the knowledge of one skilled in the art to effect such feature, structure, or characteristic in connection with other implementations whether or not explicitly described herein.
  • FB Face Beautification
  • GPU graphics processing unit
  • FB cloud-based face beautification
  • the analytic information utilized in such a FB pipe may include face shape, facial landmark points and a skin tone score.
  • the pipe may combine information of face shape, facial landmark points and skin tone score and may utilize a GPU sampler engine fully.
  • the FB pipe presented here can still achieve real-time performance on HD-resolution video with a rich processing feature set on mobile platform.
  • the FB pipe is an intelligent FB solution where customized processing is embedded. That is, the features with corresponding levels of processing to be applied to users may be differentiated by gender/age/racial under different environments are selected automatically and visually suitable/pleasant augmented results are obtained.
  • some of the implementations described herein may demonstrate a cloud-based face beautification solution for platforms that do not themselves have GPUs including such a face beautification (FB) pipe.
  • FB face beautification
  • some of the implementations described herein may present a cloud-based FB solution with low power consumption with the idea of customizing the virtual graphics device on the server side.
  • the low power server configuration may be generalized to other usages such as transcoding, video summarization, gaming, etc.
  • FIG. 1 illustrates diagram of a face beautification (FB) video augmentation pipe 100 (the features set are not limited by this diagram).
  • the whole pipe 100 is deployed on a graphics processor (e.g., with GPGPU kernels and GPU fixed function).
  • the beautification features in video augmentation pipe 100 may be based on analytic information of skin-tone likelihood/score or facial landmark points.
  • the whole process can be split to five areas: video pre-processing, application of skin tone based filters, application of facial landmark based filters, face recognition/profile detection filter, and display of the processed video and/or encoding for transmission.
  • the input video 101 (captured by camera or video clip) is firstly sent to the GPU video augmentation pipe 100 for skin tone detection (see VEBox-STD 102 and box filter 104 ) as well as facial shape/feature extraction (face detection 106 and landmark detection 108 ).
  • the skin tone detection may be done on GPU fixed function (video enhancement box 102 ).
  • the facial shape/feature extraction kernels 106 / 108 may be dispatched to execution unit on GPU.
  • skin tone based filters may include face brightening 110 , face whitening 112 , skin tone enhancement 114 , skin foundation 116 , skin smoothing 118 , the like, and/or combinations thereof (Note: the feature set may be expanded and/or the order of this feature set might be changed).
  • the processed skin tone map from skin tone detection and box filter modules 102 / 104 will be consumed by these filters. Algorithm flow charts of skin foundation filter 116 and skin smoothing filter 118 are illustrated below.
  • the landmark based filters include red lip filter 120 , big eyes filter 122 , slim face filter 124 , cute nose filter 126 , happy/sad face filter 128 , eye wrinkle remover filter 130 , eye bags remover filter 132 , dark eye circles remover filter 134 , the like, and/or combinations thereof.
  • Algorithm flow charts of the algorithm flow charts of red lip filter 120 , big eyes filter 122 , slim face filter 124 are illustrated below.
  • the face recognition/profile detection filter 140 may be optional. If face recognition/profile detection filter 140 is turned on, face recognition/profile detection will be used to customize the feature set. For example, when gender detection is on, red lip filter 120 may be turned off for male. Further, when face recognition/profile detection filter 140 is on, a user may be able to customize the setting (filter on/off, filter strength, etc.) and save the configuration for future use. That is, the features with corresponding levels of processing to be applied to users may be differentiated by gender/age/racial under different environments are selected automatically and visually suitable/pleasant augmented results are obtained.
  • the processed picture 141 may be shown on a display and/or encoded and transmitted.
  • the video augmentation pipe 100 may leverage existing fixed-function STDE hardware (e.g., Skin Tone Detection and Enhancement 102 module) on a GPU, which may be low-power and high-performance to generate the skin-tone likelihood.
  • STDE hardware e.g., Skin Tone Detection and Enhancement module
  • FIG. 6 please refer to U.S. Pat. No. 8,493,402, filed Jan. 6, 2011, and titled “System, method and computer program product for color processing of point-of-interest color”.
  • facial landmark points may leverages both a face detector, e.g., please refer to PCT Application No. PCT/CN2014/075165, filed Apr. 11, 2014, entitled “OBJECT DETECTION USING DIRECTIONAL FILTERING”, and fixed-function hardware (e.g., Convolution Filter), e.g., please refer to PCT Application No. PCT/CN2012/086840, filed Dec. 18, 2012, entitled “HARDWARE CONVOLUTION PRE-FILTER TO ACCELERATE OBJECT DETECTION”, for the face detection 106 task, which may be performed prior to facial landmark 108 detection.
  • the face detection 106 approach taken here can achieve fast-compute and low-power target while maintaining excellent detection accuracy.
  • a light-weight compute of facial landmark validation step may be embedded in the facial landmark 108 generation block to intelligently switch between detection and tracking mode. This automatic switch between tracking and detection mode may help reduce the compute while maintaining good accuracy in terms of locating facial landmark.
  • GPU based face detection may combine GPU based face detection, skin tone detection, facial landmark detection and fully utilizes GPU hardware (e.g., Sampler engine, EU, Fixed Function, etc.) to build one power efficient real-time face beautification pipe on HD-resolution video.
  • GPU hardware e.g., Sampler engine, EU, Fixed Function, etc.
  • a face beautification video augmentation pipe 100 achieve real-time (e.g., 30 fps) on HD video with very low CPU utilization and can use multiple face beautification filters simultaneously.
  • FB face beautification
  • FIG. 2 illustrates an example flow diagram 200 of face based video augmentation on a graphics processor.
  • the blocks 202 and 204 represent the analytic components (e.g., a skin tone logic unit 202 to generate skin-tone likelihood/score and a facial feature logic unit 204 to generate facial landmark points) of the system; the blocks 206 represent the features utilizing skin-tone likelihood information while the blocks 208 represent the features utilizing the facial landmark information.
  • analytic components e.g., a skin tone logic unit 202 to generate skin-tone likelihood/score and a facial feature logic unit 204 to generate facial landmark points
  • the Skin-Tone Detection (STD) 102 utilizes Video Enhancement Box (VEBox) Skin-Tone Detection and Enhancement (STDE) in a graphics processor to perform skin tone color detection for an input YUV data.
  • VEBox Video Enhancement Box
  • STDE Skin-Tone Detection and Enhancement
  • the output of the STD contains is skin-tone likelihood score represented in 5-bit for each pixel within an input frame.
  • the input of the Box-Filter 104 is the skin-tone score result from Skin-Tone Detection (STD) 102 (e.g., VEBox).
  • STD Skin-Tone Detection
  • Box-Filter 104 performs averaging operation on the input skin-tone score to produce a smooth version of skin-tone likelihood score.
  • the Face Detection 106 takes YUV input and applies a pre-trained model, which only operates on Y-channel information to identify the appearance of human faces within an input frame. Face Detection 106 returns the location and size of each detected face. In some implementations, face detection 106 may be implemented as a combination of hardware and software solutions.
  • the Facial Landmark Detection/Tracking 108 takes YUV input and information of detected faces from the Face Detection 106 .
  • Facial Landmark Detection/Tracking 108 applies a pre-trained model on the rectangle area of each detected face to detect/track the locations of a set of pre-defined facial landmark points (e.g., point of corners of eyes, points of the corners of the lip . . . etc.).
  • the output of the Facial Landmark Detection/Tracking 108 contains the locations of the set (e.g., N points) of facial landmark points.
  • the Face Brightening 110 takes YUV input data and performs adjustment on Y data based on the skin-tone likelihood/score information fed from the analytic module Skin-Tone Detection (STD) 102 to produce brightening effect of the input frame.
  • STD Skin-Tone Detection
  • the Face Whitening 112 module takes YUV input data and blends the input with a white color map.
  • the white color map is input content-adaptive and is generated within the Face Whitening 112 module.
  • the blending of the input pixels and the white color map is per-pixel wise, adaptive to the Y value of each pixel.
  • the Skin-Tone-Enhancement (STE) 114 utilizes Skin-Tone Detection (STD) 102 (e.g., VEBox) to perform the saturation enhancement on the skin-tone-color pixels where the enhancement is adaptive to the skin-tone likelihood score.
  • STD Skin-Tone Detection
  • the Skin Foundation 116 module takes YUV input data and blends the input with a user-selected foundation color where the per-pixel skin-tone likelihood score serves as the blending factor here.
  • the Skin Smoothing 118 takes YUV input data and adjusts all 3-channel information to produce a smooth version of the input.
  • the Red Lip 120 module takes YUV input data. With the facial landmark information fed into the Red Lip 120 module, the module identifies the lip area of the face if there is a face within the input frame. For input frame with detected faces, Red Lip 120 module further performs color modification for lip area so that a visually pleasant appearance of the users' lips can be obtained.
  • the Big Eyes 122 module takes YUV input data. With the facial landmark information fed into the Big Eyes 122 module and the users' preference of level of enlargement input from the Application, the Big Eyes 122 module internally derives the proper location within the face and the shape of the eyes users intend to have. Morphological warping is performed following to create the big eyes effect.
  • the Slim Face 124 module takes YUV input data. With the facial landmark information fed into the Slim Face 124 module and the users' preference of level of slim-face-effect input from the Application, the Slim Face 124 module internally derives the thinner-shape of the original face area and performs morphological warping to create the slim face effect.
  • the Cute Nose 126 module takes YUV input data. With the facial landmark information fed into the Cute Nose 126 module and the users' preference of level of adjustment input from the Application, the Cute Nose 126 module internally derives the modified shape of the nose area and performs morphological warping to create the narrower/cuter nose effect.
  • the Happy/Sad 128 module takes YUV input data. With the facial landmark information fed into the Happy/Sad 128 module and the users' preference of level of adjustment input from the Application, the Happy/Sad 128 module internally derives the modified shape of the mouth area and performs morphological warping to create the happy/sad face effect via changing the shape of users' mouths.
  • the Eye Wrinkles Removal 130 module takes YUV input data. Facial landmark information, rectangle region of the detected face, and Y-channel signal analysis are utilized by the Eye Wrinkles Removal 130 module to locate the area around eyes for processing. Once identifying the target area, a smoothing process is operated on YUV values for pixels within the area to create the wrinkles removal effect.
  • the Eye Bags Removal 132 module takes YUV input data. Facial landmark information and Y-channel signal analysis are utilized by the Eye Bags Removal 132 module to locate the eye bags regions for processing. Once identifying the regions, a smoothing process is operated on YUV values for pixels within the regions to create the eye bags removal effect.
  • the Dark Eye Circles Removal 134 block takes YUV input data. Facial landmark information and Y-channel signal analysis are utilized by the Dark Eye Circles Removal 134 to locate the eye bags region for processing. Once identifying the regions, a content-adaptive blending is performed to blend the original YUV values and a pre-defined color value for pixels within the eye bags region. The effect of removing dark eye circles is finally resulted.
  • the skin-tone enhancement feature 206 shown in FIG. 2 may leverage the existing fixed-function hardware (e.g., Skin Tone Detection and Enhancement 102 module) on a GPU, which is low-power and high-performance solution for color enhancement.
  • the facial landmark feature 208 specifically for all modules where warping operation is involved (e.g., Big Eyes, Slim Face, Cute Nose, Happy/Sad Face), may leverage a fixed-function sampler engine (see FIG. 3 ) on a GPU may be utilized to do the warping operation.
  • the pipe 100 see FIG. 1
  • the pipe 100 with rich feature set for video mode can achieve high-performance and low-power target.
  • FIG. 3 illustrates an example face beautification (FB) video augmentation scheme 300 implemented on a mobile platform GPU 302 .
  • mobile platform Graphic Processing Unit (GPU) 302 may have several available hardware blocks (e.g., independent types of engines) with distinct functionalities.
  • GPU 302 may include video codec engine(s) 304 , video processing engine(s) 306 , render/3D engine 308 , sampler engine 310 , an array of cores 312 , the like, and/or combinations thereof.
  • Video codec engine(s) 304 may perform video encoding/decoding.
  • video codec engine(s) 304 may include Decode Engines for video decoding and/or Encode Engines for video encoding.
  • Video processing engine(s) 306 may perform video pre-post-processing. For example, some parts of video augmentation pipe 100 (e.g. see skin tone detection VEBox-STD 102 and skin tone enhancement VEBox-STE 114 of FIG. 1 ) may be implemented via video processing engine(s) 306 . Most of the rest of video augmentation pipe 100 may be implemented via array of cores 312 , as illustrated.
  • Render/3D engine 308 in combination with array of cores 312 may perform rendering, gaming, the like, and/or combinations thereof.
  • Sampler engine 310 is a separate module (e.g., separate from video processing engine 306 ) inside GPU 302 .
  • sampler engine 310 may be implemented as a hardware module to allow quick sampling access to get the pixels/texels from the original data map, and to allow quick filtering operations.
  • FIG. 4 illustrates an example of a flexible virtual GPU 400 configuration implemented on a sever platform GPU 402 .
  • flexible virtual GPU 400 may include several virtual GPUs 412 (e.g., VM_ 0 , VM_ 1 , and VM_ 2 ) that share one physical GPU 402 .
  • a first virtual GPU 414 e.g., VM_ 0
  • a second virtual GPU 416 e.g., VM_ 1
  • a third virtual GPU 416 e.g., VM_ 2
  • sever platform GPU 402 may transfer input video images as well as output video images modified by the facial beatification operations described herein between one or more remote devices in communication with sever platform GPU 402 .
  • a customized virtual graphics devices may be provide via a cloud-based facial beautification solution.
  • This cloud-based facial beautification solution may have the advantage over power efficiency compared to other cloud-based FB solution which is purely CPU software solution.
  • server Graphic Processing Unit (GPU) 402 may have several available hardware blocks (e.g., independent types of engines) with distinct functionalities.
  • server GPU 402 may include the same and/or similar hardware blocks as mobile platform Graphic Processing Unit (GPU) 302 of FIG. 3 .
  • server GPU 402 may include video codec engine(s) (not shown here), video processing engine(s) 406 , render/3D engine(s) 408 , sampler engine (not shown here), an array of cores (not shown here), the like, and/or combinations thereof.
  • video codec engine(s) not shown here
  • video processing engine(s) 406 may include render/3D engine(s) 408 , sampler engine (not shown here), an array of cores (not shown here), the like, and/or combinations thereof.
  • sampler engine not shown here
  • an array of cores not shown here
  • GPU virtualization technology may be implemented in cloud computing.
  • one powerful physical GPU 402 on the cloud side may be shared by multiple Virtual Machines (VMs) 412 .
  • VMs 412 Virtual Machines 412 exclusively owns the virtual graphics device.
  • the proposed cloud-based facial beautification solution has advantages of both performance and power efficiency compared to others due to two distinct system-wise factors.
  • the flexible virtual GPU 400 configuration allows for utilization of GPU instead of CPU; thus better performance may be achieved.
  • the flexible virtual GPU 400 configuration allows for utilization of virtual graphics devices to allow for sharing of the GPU with other workloads; thus a minimum of power leak may be achieved.
  • FIGS. 5-9 may apply skin tone based filters.
  • Skin tone based filters may include face brightening, face whitening, skin tone enhancement, skin foundation and skin smoothing, the like, and/or combinations thereof.
  • the processed skin tone map from discussed above may be consumed by these filters.
  • FIG. 5 illustrates an example skin smooth filter flow chart 500 .
  • skin smooth filter 500 may take YUV input data and adjust all 3-channel information to produce a smooth version of the input.
  • FIG. 6 illustrates an example foundation color filter flow chart 600 .
  • foundation color filter 600 may take YUV input data and blend the input with a user-selected foundation color where the per-pixel skin-tone likelihood score serves as the blending factor here.
  • FIG. 7 illustrates an example skin tone enhancement filter flow chart 700 .
  • skin tone enhancement filter 700 may utilize Skin-Tone Detection (STD) 102 (See FIG. 1 ) to perform the saturation enhancement on the skin-tone-color pixels where the enhancement is adaptive to the skin-tone likelihood score.
  • STD Skin-Tone Detection
  • Delta-U and Delta-V is the delta of chroma components from Skin-Tone Detection (STD) 102 (See FIG. 1 ).
  • FIG. 8 illustrates an example face brightening filter flow chart 800 .
  • face brightening filter 800 may take YUV input data and perform adjustment on Y data based on the skin-tone likelihood/score information fed from the analytic module Skin-Tone Detection (STD) 102 to produce brightening effect of the input frame.
  • Skin-Tone Detection STD
  • Delta-Y is the delta of luma component.
  • FIG. 9 illustrates an example face whitening filter flow chart 900 .
  • face whitening filter 900 may take YUV input data and blend the input with a white color map.
  • the white color map is input content-adaptive and is generated within the Face Whitening 112 module.
  • the blending of the input pixels and the white color map is per-pixel wise, adaptive to the Y value of each pixel.
  • Py is the luma component.
  • FIG. 10 is an illustrative diagram of an example red lip filter flow chart 1000 .
  • red lip filter 1000 may take YUV input data. With the facial landmark information fed into the red lip filter 1000 , the red lip filter 1000 may identify the lip area of the face if there is a face within the input frame. For input frame with detected faces, red lip filter 1000 may further perform color modification for lip area so that a visually pleasant appearance of the users' lips can be obtained.
  • FIG. 12 is an illustrative diagram of an example big eyes filter flow chart 1200 .
  • big eyes filter 1200 may utilize the parameters R, C, d and s described above in FIG. 11 .
  • big eyes filter 1200 may take YUV input data. With the facial landmark information fed into the big eyes filter 1200 and the users' preference of level of enlargement input from the Application, big eyes filter 1200 may internally derive the proper location within the face and the shape of the eyes users intend to have. Morphological warping may be performed following to create the big eyes effect.
  • FIG. 13 is an illustrative diagram of an example slim face filter flow chart 1300 .
  • slim face filter 1300 may utilize the parameters R, C, CM, d and s described above in FIG. 11 .
  • slim face filter 1300 take YUV input data. With the facial landmark information fed into the slim face filter 1300 and the users' preference of level of slim-face-effect input from the Application, the slim face filter 1300 may internally derive the thinner-shape of the original face area and perform morphological warping to create the slim face effect.
  • FIG. 14 provides an illustrative diagram of an example face beautification process, arranged in accordance with at least some implementations of the present disclosure.
  • process 1400 may include one or more operations, functions or actions as illustrated by one or more of blocks 1402 , etc.
  • process 1400 will be described herein with reference to example video augmentation pipe 100 of FIG. 1 .
  • Process 1400 may be utilized as a computer-implemented method for video coding.
  • Process 1800 may begin at block 1402 , “DETERMINE SKIN TONE LIKELIHOOD/SCORE ON INPUT VIDEO IMAGES”, where a skin tone likelihood/score may be determined.
  • skin tone likelihood/score may be determined via a skin tone logic unit.
  • Processing may continue from operation 1402 to operation 1404 , “PERFORM FACIAL DETECTION ON THE INPUT VIDEO IMAGES”, where facial detection may be performed.
  • facial detection may be performed via a facial feature logic unit.
  • Processing may continue from operation 1404 to operation 1406 , “PERFORM FACIAL LANDMARK DETECTION AND/OR TRACKING ON THE INPUT VIDEO IMAGES BASED AT LEAST IN PART ON THE FACIAL DETECTION”, where facial landmark detection and/or tracking may be performed.
  • facial landmark detection and/or tracking may be performed based at least in part on the facial detection via the facial feature logic unit.
  • Processing may continue from operation 1404 to operation 1406 , “MODIFY THE INPUT VIDEO IMAGES BY FACIAL BEAUTIFICATION INTO OUTPUT VIDEO IMAGES”, where facial beautification may be performed.
  • facial beautification may be performed based at least in part on the skin tone likelihood/score and the facial landmark detection via a beautification module.
  • process 1400 may be illustrated in one or more examples of implementations discussed in greater detail below with regard to FIG. 15 .
  • FIG. 15 provides an illustrative diagram of an example video augmentation system 1600 (see, e.g., FIG. 16 for more details) and face beautification process 1500 in operation, arranged in accordance with at least some implementations of the present disclosure.
  • Process 1500 may include one or more operations, functions or actions as illustrated by one or more of operations 1510 , etc.
  • process 1500 will be described herein with reference to example video augmentation system 1600 including video augmentation system pipe 100 of FIG. 1 , as is discussed further herein below with respect to FIG. 16 .
  • Process 1500 may begin at operation 1512 , “RECEIVE INPUT VIDEO IMAGES”, where input video images may be received.
  • input video images may be received via the skin tone logic unit 202 , the facial feature logic unit 204 , and/or the beautification module 206 / 208 .
  • Process 1500 may continue at operation 1514 , “PERFORM SKIN TONE DETECTION”, where a skin tone likelihood score may be determined.
  • skin tone likelihood score may be determined from the input video images via skin tone logic unit 202 .
  • Process 1500 may continue at operation 1516 , “SMOOTH SKIN TONE SCORE”, where the skin tone likelihood score may be smoothed.
  • the skin tone likelihood score may be smoothed via the skin tone logic unit 202 .
  • skin tone likelihood score 1518 from skin tone logic unit 202 may be output to skin tone beatification module 206 .
  • Process 1500 may continue at operation 1520 , “FACE DETECTION”, where facial detection may be performed.
  • facial detection may be performed on the input video images via the facial feature logic unit 204 .
  • Process 1500 may continue at operation 1522 , “LANDMARK DETECTION AND/OR TRACKING”, where facial landmark detection and/or tracking may be performed.
  • facial landmark detection and/or tracking may be performed on the input video images based at least in part on the facial detection via the facial feature logic unit 204 .
  • landmark point data 1524 from facial feature logic unit 204 may be output to landmark beatification module 208 .
  • Process 1500 may continue at operation 1528 , “FACIAL RECOGNITION PROFILE DETECTION”, where facial recognition profile detection may be performed.
  • facial recognition profile detection may be performed via profile detection module 140 based at least in part on the face detection.
  • strength settings 1530 from profile detection module 140 may be output to skin tone beatification module 206 and or to landmark beatification module 208 .
  • profile detection module 140 may modify strength settings associated with various facial beatification operations based at least in part on the face detection. For example, profile detection module 140 may modify the strength settings based at least in part on one or more of the following detected facial attributes: gender, age, and race.
  • strength settings 1530 may instead be preset and/or be specified by a user's preference and may be output to skin tone beatification module 206 and or to landmark beatification module 208 .
  • Process 1500 may continue at operation 1532 , “BRIGHTENING”; operation 1534 , “WHITENING”; operation 1536 , “ENHANCEMENT”; operation 1538 , “FOUNDATION”; and operation 1540 , “SMOOTHING”.
  • beautification module 206 / 208 may modify the input video images by facial beautification into output video images based at least in part on the skin tone likelihood score and/or the facial landmark detection.
  • one or more of the following skin tone beautification operations may be performed via skin tone beautification portion 206 of the beautification module 204 / 206 based at least in part on the strength settings.
  • skin tone beautification operations skin tone enhancement, skin foundation, and skin smoothing
  • skin tone beautification portion 206 of the beautification module 204 / 206 may be performed via skin tone beautification portion 206 of the beautification module 204 / 206 based at least in part on the skin tone likelihood score.
  • operations 1532 , 1534 , 1536 , 1538 , and 1540 may be done sequentially, so that the output of one operation (e.g., operation 1532 ) may be used as the input video image to start the next operation (e.g., operation 1534 ).
  • the above examples may include specific combination of features. However, such the above examples are not limited in this regard and, in various implementations, the above examples may include the undertaking only a subset of such features, undertaking a different order of such features, undertaking a different combination of such features, and/or undertaking additional features than those features explicitly listed.
  • output video images 1541 modified by skin tone beautification may be output to landmark beatification module 208 .
  • Process 1500 may continue at operation 1542 , “RED LIP”; operation 1544 , “BIG EYES”; operation 1546 , “SLIM FACE”; operation 1548 , “CUTE NOSE”; operation 1550 , “HAPPY/SAD FACE”; operation 1552 , “EYE WRINKLE REMOVA”; operation 1554 , “EYE BAGS REMOVAL”; and operation 1556 , “DARK EYE CIRCLES REMOVAL”.
  • one or more of the following landmark beautification operations may be performed via a landmark beautification portion 208 of the beautification module 206 / 208 based at least in part on the strength settings and the landmark points.
  • operations 1542 , 1544 , 1546 , 1548 , 1550 , 1552 , 1554 , and 1556 may be done sequentially, so that the output of one operation (e.g., operation 1552 ) may be used as the input video image to start the next operation (e.g., operation 1554 ).
  • the above examples may include specific combination of features. However, such the above examples are not limited in this regard and, in various implementations, the above examples may include the undertaking only a subset of such features, undertaking a different order of such features, undertaking a different combination of such features, and/or undertaking additional features than those features explicitly listed.
  • output video images 1558 modified by landmark beautification may be output to display 141 .
  • Such output video images 1558 modified by landmark beautification may be output for transmission to one or more remote devices (not illustrated here).
  • Process 1500 may continue at operation 1560 , “DISPLAY MODIFIED OUTPUT VIDEO IMAGES”, where the modified output video images may be displayed.
  • the modified output video images as modified by the beautification module 206 / 208 may be displayed via display 141 .
  • video augmentation pipe 100 may be implemented on a mobile platform type GPU.
  • video augmentation pipe 100 may be implemented on a server platform type GPU.
  • the server platform type GPU may include several virtual GPUs that may share one physical GPU.
  • the server platform type GPU may be configured to transfer input video images as well as output video images modified by the facial beatification operations between one or more remote devices (not shown) in communication with sever platform GPU.
  • Various components of the systems and/or processes described herein may be implemented in software, firmware, and/or hardware and/or any combination thereof.
  • various components of the systems and/or processes described herein may be provided, at least in part, by hardware of a computing System-on-a-Chip (SoC) such as may be found in a computing system such as, for example, a smart phone.
  • SoC System-on-a-Chip
  • module may refer to a “component” or to a “logic unit”, as these terms are described below. Accordingly, the term “module” may refer to any combination of software logic, firmware logic, and/or hardware logic configured to provide the functionality described herein. For example, one of ordinary skill in the art will appreciate that operations performed by hardware and/or firmware may alternatively be implemented via a software component, which may be embodied as a software package, code and/or instruction set, and also appreciate that a logic unit may also utilize a portion of software to implement its functionality.
  • the term “component” refers to any combination of software logic and/or firmware logic configured to provide the functionality described herein.
  • the software logic may be embodied as a software package, code and/or instruction set, and/or firmware that stores instructions executed by programmable circuitry.
  • the components may, collectively or individually, be embodied for implementation as part of a larger system, for example, an integrated circuit (IC), system on-chip (SoC), and so forth.
  • IC integrated circuit
  • SoC system on-chip
  • logic unit refers to any combination of firmware logic and/or hardware logic configured to provide the functionality described herein.
  • the “hardware”, as used in any implementation described herein, may include, for example, singly or in any combination, hardwired circuitry, programmable circuitry, state machine circuitry, and/or firmware that stores instructions executed by programmable circuitry.
  • the logic units may, collectively or individually, be embodied as circuitry that forms part of a larger system, for example, an integrated circuit (IC), system on-chip (SoC), and so forth.
  • IC integrated circuit
  • SoC system on-chip
  • a logic unit may be embodied in logic circuitry for the implementation firmware or hardware of the systems discussed herein.
  • operations performed by hardware and/or firmware may also utilize a portion of software to implement the functionality of the logic unit.
  • any one or more of the blocks of the processes described herein may be undertaken in response to instructions provided by one or more computer program products.
  • Such program products may include signal bearing media providing instructions that, when executed by, for example, a processor, may provide the functionality described herein.
  • the computer program products may be provided in any form of computer readable medium.
  • a processor including one or more processor core(s) may undertake one or more operations in response to instructions conveyed to the processor by a computer readable medium.
  • FIG. 16 is an illustrative diagram of an example graphics processing system 1600 , arranged in accordance with at least some implementations of the present disclosure.
  • graphics processing system 1600 may include one or more processors 1602 , one or more memory stores 1604 , GPUs 1606 , display 1608 to provide images 1609 , logic modules 1610 , coder 1612 , and/or antenna 1614 .
  • processors 1602 , memory store 1604 , GPU 1606 , display 1608 , coder 1612 , and/or antenna 1614 may be capable of communication with one another and/or communication with portions of logic modules 1610 .
  • graphics processing system 1600 may include antenna 1612 .
  • antenna 1612 may be configured to transmit or receive an encoded bitstream of video data, for example.
  • Processor(s) 1602 and/or GPU(s) 1006 may be any type of processor and/or processing unit.
  • processor(s) 1602 may include distinct central processing units, distinct graphic processing units, integrated system-on-a-chip (SoC) architectures, the like, and/or combinations thereof.
  • SoC system-on-a-chip
  • memory store(s) 1608 may be any type of memory.
  • memory store(s) 1604 may be volatile memory (e.g., Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), etc.) or non-volatile memory (e.g., flash memory, etc.), and so forth.
  • memory store(s) 1604 may be implemented by cache memory.
  • graphics processing system 1600 may include display device 168 .
  • Display device 1608 may be configured to present video data as images 1609 .
  • logic modules 1610 may embody various modules as discussed with respect to any system or subsystem described herein.
  • some of logic modules 1610 may be implemented in hardware, while software may implement other logic modules.
  • some of logic modules 1610 may be implemented by application-specific integrated circuit (ASIC) logic while other logic modules may be provided by software instructions executed by logic such as GPU 1606 , for example.
  • ASIC application-specific integrated circuit
  • GPU 1606 for example.
  • present disclosure is not limited in this regard and some of logic modules 1610 may be implemented by any combination of hardware, firmware and/or software.
  • logic modules 1610 may include a video augmentation pipe 100 , and/or the like configured to implement operations of one or more of the implementations described herein.
  • FIG. 17 is an illustrative diagram of an example system 1700 , arranged in accordance with at least some implementations of the present disclosure.
  • system 1700 may be a media system although system 1700 is not limited to this context.
  • system 1700 may be incorporated into a personal computer (PC), laptop computer, ultra-laptop computer, tablet, touch pad, portable computer, handheld computer, palmtop computer, personal digital assistant (PDA), cellular telephone, combination cellular telephone/PDA, television, smart device (e.g., smart phone, smart tablet or smart television), mobile internet device (MID), messaging device, data communication device, cameras (e.g. point-and-shoot cameras, super-zoom cameras, digital single-lens reflex (DSLR) cameras), and so forth.
  • PC personal computer
  • laptop computer ultra-laptop computer
  • tablet touch pad
  • portable computer handheld computer
  • palmtop computer personal digital assistant
  • MID mobile internet device
  • MID mobile internet device
  • MID mobile internet device
  • MID mobile internet device
  • MID smart internet
  • system 1700 includes a platform 1702 coupled to a display 1720 .
  • Platform 1702 may receive content from a content device such as content services device(s) 1730 or content delivery device(s) 1740 or other similar content sources.
  • a navigation controller 1750 including one or more navigation features may be used to interact with, for example, platform 1702 and/or display 1720 . Each of these components is described in greater detail below.
  • platform 1702 may include any combination of a chipset 1705 , processor 1710 , memory 1712 , antenna 1713 , storage 1714 , graphics subsystem 1715 , applications 1716 and/or radio 1718 .
  • Chipset 1705 may provide intercommunication among processor 1710 , memory 1712 , storage 1714 , graphics subsystem 1715 , applications 1716 and/or radio 1718 .
  • chipset 1705 may include a storage adapter (not depicted) capable of providing intercommunication with storage 1714 .
  • Processor 1710 may be implemented as a Complex Instruction Set Computer (CISC) or Reduced Instruction Set Computer (RISC) processors, x86 instruction set compatible processors, multi-core, or any other microprocessor or central processing unit (CPU). In various implementations, processor 1710 may be dual-core processor(s), dual-core mobile processor(s), and so forth.
  • CISC Complex Instruction Set Computer
  • RISC Reduced Instruction Set Computer
  • processor 1710 may be dual-core processor(s), dual-core mobile processor(s), and so forth.
  • Memory 1712 may be implemented as a volatile memory device such as, but not limited to, a Random Access Memory (RAM), Dynamic Random Access Memory (DRAM), or Static RAM (SRAM).
  • RAM Random Access Memory
  • DRAM Dynamic Random Access Memory
  • SRAM Static RAM
  • Storage 1714 may be implemented as a non-volatile storage device such as, but not limited to, a magnetic disk drive, optical disk drive, tape drive, an internal storage device, an attached storage device, flash memory, battery backed-up SDRAM (synchronous DRAM), and/or a network accessible storage device.
  • storage 1714 may include technology to increase the storage performance enhanced protection for valuable digital media when multiple hard drives are included, for example.
  • Graphics subsystem 1715 may perform processing of images such as still or video for display.
  • Graphics subsystem 1715 may be a graphics processing unit (GPU) or a visual processing unit (VPU), for example.
  • An analog or digital interface may be used to communicatively couple graphics subsystem 1715 and display 1720 .
  • the interface may be any of a High-Definition Multimedia Interface, DisplayPort, wireless HDMI, and/or wireless HD compliant techniques.
  • Graphics subsystem 1715 may be integrated into processor 1710 or chipset 1705 .
  • graphics subsystem 1715 may be a stand-alone device communicatively coupled to chipset 1705 .
  • graphics and/or video processing techniques described herein may be implemented in various hardware architectures.
  • graphics and/or video functionality may be integrated within a chipset.
  • a discrete graphics and/or video processor may be used.
  • the graphics and/or video functions may be provided by a general purpose processor, including a multi-core processor.
  • the functions may be implemented in a consumer electronics device.
  • Radio 1718 may include one or more radios capable of transmitting and receiving signals using various suitable wireless communications techniques. Such techniques may involve communications across one or more wireless networks.
  • Example wireless networks include (but are not limited to) wireless local area networks (WLANs), wireless personal area networks (WPANs), wireless metropolitan area network (WMANs), cellular networks, and satellite networks. In communicating across such networks, radio 1718 may operate in accordance with one or more applicable standards in any version.
  • display 1720 may include any television type monitor or display.
  • Display 1720 may include, for example, a computer display screen, touch screen display, video monitor, television-like device, and/or a television.
  • Display 1720 may be digital and/or analog.
  • display 1720 may be a holographic display.
  • display 1720 may be a transparent surface that may receive a visual projection.
  • projections may convey various forms of information, images, and/or objects.
  • projections may be a visual overlay for a mobile augmented reality (MAR) application.
  • MAR mobile augmented reality
  • platform 1702 may display user interface 1722 on display 1720 .
  • MAR mobile augmented reality
  • content services device(s) 1730 may be hosted by any national, international and/or independent service and thus accessible to platform 1702 via the Internet, for example.
  • Content services device(s) 1730 may be coupled to platform 1702 and/or to display 1720 .
  • Platform 1702 and/or content services device(s) 1730 may be coupled to a network 1760 to communicate (e.g., send and/or receive) media information to and from network 1760 .
  • Content delivery device(s) 1740 also may be coupled to platform 1702 and/or to display 1720 .
  • content services device(s) 1730 may include a cable television box, personal computer, network, telephone, Internet enabled devices or appliance capable of delivering digital information and/or content, and any other similar device capable of unidirectionally or bidirectionally communicating content between content providers and platform 1702 and/display 1720 , via network 1760 or directly. It will be appreciated that the content may be communicated unidirectionally and/or bidirectionally to and from any one of the components in system 1700 and a content provider via network 1760 . Examples of content may include any media information including, for example, video, music, medical and gaming information, and so forth.
  • Content services device(s) 1730 may receive content such as cable television programming including media information, digital information, and/or other content.
  • content providers may include any cable or satellite television or radio or Internet content providers. The provided examples are not meant to limit implementations in accordance with the present disclosure in any way.
  • platform 1702 may receive control signals from navigation controller 1750 having one or more navigation features.
  • the navigation features of controller 1750 may be used to interact with user interface 1722 , for example.
  • navigation controller 1750 may be a pointing device that may be a computer hardware component (specifically, a human interface device) that allows a user to input spatial (e.g., continuous and multi-dimensional) data into a computer.
  • GUI graphical user interfaces
  • televisions and monitors allow the user to control and provide data to the computer or television using physical gestures.
  • Movements of the navigation features of controller 1750 may be replicated on a display (e.g., display 1720 ) by movements of a pointer, cursor, focus ring, or other visual indicators displayed on the display.
  • a display e.g., display 1720
  • the navigation features located on navigation controller 1750 may be mapped to virtual navigation features displayed on user interface 1722 .
  • controller 1750 may not be a separate component but may be integrated into platform 1702 and/or display 1720 . The present disclosure, however, is not limited to the elements or in the context shown or described herein.
  • drivers may include technology to enable users to instantly turn on and off platform 1702 like a television with the touch of a button after initial boot-up, when enabled, for example.
  • Program logic may allow platform 1702 to stream content to media adaptors or other content services device(s) 1730 or content delivery device(s) 1740 even when the platform is turned “off.”
  • chipset 1705 may include hardware and/or software support for (5.1) surround sound audio and/or high definition (7.1) surround sound audio, for example.
  • Drivers may include a graphics driver for integrated graphics platforms.
  • the graphics driver may comprise a peripheral component interconnect (PCI) Express graphics card.
  • PCI peripheral component interconnect
  • any one or more of the components shown in system 1700 may be integrated.
  • platform 1702 and content services device(s) 1730 may be integrated, or platform 1702 and content delivery device(s) 1740 may be integrated, or platform 1702 , content services device(s) 1730 , and content delivery device(s) 1740 may be integrated, for example.
  • platform 1702 and display 1720 may be an integrated unit. Display 1720 and content service device(s) 1730 may be integrated, or display 1720 and content delivery device(s) 1740 may be integrated, for example. These examples are not meant to limit the present disclosure.
  • system 1700 may be implemented as a wireless system, a wired system, or a combination of both.
  • system 1700 may include components and interfaces suitable for communicating over a wireless shared media, such as one or more antennas, transmitters, receivers, transceivers, amplifiers, filters, control logic, and so forth.
  • a wireless shared media may include portions of a wireless spectrum, such as the RF spectrum and so forth.
  • Platform 1702 may establish one or more logical or physical channels to communicate information.
  • the information may include media information and control information.
  • Media information may refer to any data representing content meant for a user. Examples of content may include, for example, data from a voice conversation, videoconference, streaming video, electronic mail (“email”) message, voice mail message, alphanumeric symbols, graphics, image, video, text and so forth. Data from a voice conversation may be, for example, speech information, silence periods, background noise, comfort noise, tones and so forth.
  • Control information may refer to any data representing commands, instructions or control words meant for an automated system. For example, control information may be used to route media information through a system, or instruct a node to process the media information in a predetermined manner. The embodiments, however, are not limited to the elements or in the context shown or described in FIG. 17 .
  • system 1700 may be embodied in varying physical styles or form factors.
  • FIG. 18 illustrates implementations of a small form factor device 1800 in which system 1800 may be embodied.
  • device 1800 may be implemented as a mobile computing device a having wireless capabilities.
  • a mobile computing device may refer to any device having a processing system and a mobile power source or supply, such as one or more batteries, for example.
  • examples of a mobile computing device may include a personal computer (PC), laptop computer, ultra-laptop computer, tablet, touch pad, portable computer, handheld computer, palmtop computer, personal digital assistant (PDA), cellular telephone, combination cellular telephone/PDA, television, smart device (e.g., smart phone, smart tablet or smart television), mobile internet device (MID), messaging device, data communication device, cameras (e.g. point-and-shoot cameras, super-zoom cameras, digital single-lens reflex (DSLR) cameras), and so forth.
  • PC personal computer
  • laptop computer ultra-laptop computer
  • tablet touch pad
  • portable computer handheld computer
  • palmtop computer personal digital assistant
  • MID mobile internet device
  • Examples of a mobile computing device also may include computers that are arranged to be worn by a person, such as a wrist computer, finger computer, ring computer, eyeglass computer, belt-clip computer, arm-band computer, shoe computers, clothing computers, and other wearable computers.
  • a mobile computing device may be implemented as a smart phone capable of executing computer applications, as well as voice communications and/or data communications.
  • voice communications and/or data communications may be described with a mobile computing device implemented as a smart phone by way of example, it may be appreciated that other embodiments may be implemented using other wireless mobile computing devices as well. The embodiments are not limited in this context.
  • device 1800 may include a housing 1802 , a display 1804 which may include a user interface 1810 , an input/output (I/O) device 1806 , and an antenna 1808 .
  • Device 1800 also may include navigation features 1812 .
  • Display 1804 may include any suitable display unit for displaying information appropriate for a mobile computing device.
  • I/O device 1806 may include any suitable I/O device for entering information into a mobile computing device. Examples for I/O device 1806 may include an alphanumeric keyboard, a numeric keypad, a touch pad, input keys, buttons, switches, rocker switches, microphones, speakers, voice recognition device and software, image sensors, and so forth.
  • Information also may be entered into device 1800 by way of microphone (not shown). Such information may be digitized by a voice recognition device (not shown). The embodiments are not limited in this context.
  • Various embodiments may be implemented using hardware elements, software elements, or a combination of both.
  • hardware elements may include processors, microprocessors, circuits, circuit elements (e.g., transistors, resistors, capacitors, inductors, and so forth), integrated circuits, application specific integrated circuits (ASIC), programmable logic devices (PLD), digital signal processors (DSP), field programmable gate array (FPGA), logic gates, registers, semiconductor device, chips, microchips, chip sets, and so forth.
  • Examples of software may include software components, programs, applications, computer programs, application programs, system programs, machine programs, operating system software, middleware, firmware, software modules, routines, subroutines, functions, methods, procedures, software interfaces, application program interfaces (API), instruction sets, computing code, computer code, code segments, computer code segments, words, values, symbols, or any combination thereof. Determining whether an embodiment is implemented using hardware elements and/or software elements may vary in accordance with any number of factors, such as desired computational rate, power levels, heat tolerances, processing cycle budget, input data rates, output data rates, memory resources, data bus speeds and other design or performance constraints.
  • IP cores may be stored on a tangible, machine readable medium and supplied to various customers or manufacturing facilities to load into the fabrication machines that actually make the logic or processor.
  • a computer-implemented method for video augmentation on a GPU may include determining, via a skin tone logic unit of the GPU, a skin tone likelihood score on input video images; performing, via a facial feature logic unit of the GPU, facial detection on the input video images; performing, via the facial feature logic unit, facial landmark detection and/or tracking on the input video images based at least in part on the facial detection; and modifying, via a beautification module of the GPU, the input video images by facial beautification into output video images based at least in part on the skin tone likelihood score and the facial landmark detection.
  • a computer-implemented method for video augmentation on a GPU may include where the GPU is a server platform type GPU, where the server platform type GPU includes several virtual GPUs that share one physical GPU, and where the server platform type GPU is configured to transfer input video images as well as output video images modified by the facial beatification operations between one or more remote devices in communication with sever platform GPU; receiving input video images via the skin tone logic unit, the facial feature logic unit, and the beautification module; smoothing, via the skin tone logic unit, the skin tone likelihood score; performing, via a profile detection module, facial recognition profile detection based at least in part on the face detection; modifying, via the profile detection module, strength settings associated with various facial beatification operations based at least in part on the face detection, where the strength settings may be based at least in part on one or more of the following detected facial attributes: gender, age, and race; performing, via a skin tone beautification portion of the beautification module, one or more of the following skin tone beautification operations based at least in part on the strength settings
  • a computer-implemented method for video augmentation on a GPU may include where the GPU is a mobile platform type GPU; receiving input video images via the skin tone logic unit, the facial feature logic unit, and the beautification module; smoothing, via the skin tone logic unit, the skin tone likelihood score; performing, via a profile detection module, facial recognition profile detection based at least in part on the face detection; modifying, via the profile detection module, strength settings associated with various facial beatification operations based at least in part on the face detection, where the strength settings may be based at least in part on one or more of the following detected facial attributes: gender, age, and race; performing, via a skin tone beautification portion of the beautification module, one or more of the following skin tone beautification operations based at least in part on the strength settings: face brightening, face whitening, skin tone enhancement, skin foundation, and skin smoothing, and performing one or more of the following skin tone beautification operations based at least in part on the skin tone likelihood score: skin tone enhancement, skin foundation, and skin
  • a system for video augmentation may include one or more graphics processing units, the one or more graphics processing units including a skin tone logic unit, a facial feature logic unit, and a beautification module; one or more memory stores communicatively coupled to the one or more graphics processing units; where the one or more graphics processing units are configured to: determine, via the skin tone logic unit, a skin tone likelihood score on input video images, perform, via the facial feature logic unit, facial detection on the input video images, perform, via the facial feature logic unit, facial landmark detection and/or tracking on the input video images based at least in part on the facial detection, and modify, via the beautification module, the input video images by facial beautification into output video images based at least in part on the skin tone likelihood score and the facial landmark detection.
  • the system for video augmentation may further include where the one or more graphics processing units are server platform type GPU, where the server platform type GPU includes several virtual GPUs that share one physical GPU, and where the server platform type GPU is configured to transfer input video images as well as output video images modified by the facial beatification operations between one or more remote devices in communication with sever platform GPU; where the one or more graphics processing units are configured to: receive input video images via the skin tone logic unit, the facial feature logic unit, and the beautification module; smooth, via the skin tone logic unit, the skin tone likelihood score; perform, via a profile detection module, facial recognition profile detection based at least in part on the face detection; modify, via the profile detection module, strength settings associated with various facial beatification operations based at least in part on the face detection, where the strength settings may be based at least in part on one or more of the following detected facial attributes: gender, age, and race; perform, via a skin tone beautification portion of the beautification module, one or more of the following skin tone beautification operations based at least in part
  • an apparatus for video augmentation may include a graphics processing unit (GPU), the graphics processing unit configured to: determine, via a skin tone logic unit, a skin tone likelihood score on input video images; perform, via a facial feature logic unit, facial detection on the input video images; perform, via the facial feature logic unit, facial landmark detection and/or tracking on the input video images based at least in part on the facial detection; and modify, via a beautification module, the input video images by facial beautification into output video images based at least in part on the skin tone likelihood score and the facial landmark detection.
  • GPU graphics processing unit
  • the apparatus for video augmentation may further include where the GPU is a mobile platform type GPU; where the graphics processing unit is further configured to: receive input video images via the skin tone logic unit, the facial feature logic unit, and the beautification module; smooth, via the skin tone logic unit, the skin tone likelihood score; perform, via a profile detection module, facial recognition profile detection based at least in part on the face detection; modify, via the profile detection module, strength settings associated with various facial beatification operations based at least in part on the face detection, where the strength settings may be based at least in part on one or more of the following detected facial attributes: gender, age, and race; perform, via a skin tone beautification portion of the beautification module, one or more of the following skin tone beautification operations based at least in part on the strength settings: face brightening, face whitening, skin tone enhancement, skin foundation, and skin smoothing, and performing one or more of the following skin tone beautification operations based at least in part on the skin tone likelihood score: skin tone enhancement, skin foundation, and skin smoothing
  • At least one machine-readable medium may include a plurality of instructions that in response to being executed on a computing device, causes the computing device to perform the method according to any one of the above examples.
  • an apparatus may include means for performing the methods according to any one of the above examples.
  • the above examples may include specific combination of features. However, such the above examples are not limited in this regard and, in various implementations, the above examples may include the undertaking only a subset of such features, undertaking a different order of such features, undertaking a different combination of such features, and/or undertaking additional features than those features explicitly listed. For example, all features described with respect to the example methods may be implemented with respect to the example apparatus, the example systems, and/or the example articles, and vice versa.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Graphics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Architecture (AREA)
  • Computer Hardware Design (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Image Processing (AREA)
US15/127,785 2015-09-11 2015-09-11 Scalable real-time face beautification of video images Active US10453270B2 (en)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2015/089433 WO2017041289A1 (fr) 2015-09-11 2015-09-11 Embellissement de visage en temps réel adaptable dans des images vidéo

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/089433 A-371-Of-International WO2017041289A1 (fr) 2015-09-11 2015-09-11 Embellissement de visage en temps réel adaptable dans des images vidéo

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US16/658,803 Continuation US11328496B2 (en) 2015-09-11 2019-10-21 Scalable real-time face beautification of video images

Publications (2)

Publication Number Publication Date
US20180174370A1 US20180174370A1 (en) 2018-06-21
US10453270B2 true US10453270B2 (en) 2019-10-22

Family

ID=58240507

Family Applications (4)

Application Number Title Priority Date Filing Date
US15/127,785 Active US10453270B2 (en) 2015-09-11 2015-09-11 Scalable real-time face beautification of video images
US16/658,803 Active 2036-02-15 US11328496B2 (en) 2015-09-11 2019-10-21 Scalable real-time face beautification of video images
US17/388,946 Active US11741682B2 (en) 2015-09-11 2021-07-29 Face augmentation in video
US18/456,845 Pending US20230401807A1 (en) 2015-09-11 2023-08-28 Face augmentation in video

Family Applications After (3)

Application Number Title Priority Date Filing Date
US16/658,803 Active 2036-02-15 US11328496B2 (en) 2015-09-11 2019-10-21 Scalable real-time face beautification of video images
US17/388,946 Active US11741682B2 (en) 2015-09-11 2021-07-29 Face augmentation in video
US18/456,845 Pending US20230401807A1 (en) 2015-09-11 2023-08-28 Face augmentation in video

Country Status (2)

Country Link
US (4) US10453270B2 (fr)
WO (1) WO2017041289A1 (fr)

Families Citing this family (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10453270B2 (en) * 2015-09-11 2019-10-22 Intel Corporation Scalable real-time face beautification of video images
KR102488563B1 (ko) * 2016-07-29 2023-01-17 삼성전자주식회사 차등적 뷰티효과 처리 장치 및 방법
CN107172354B (zh) * 2017-06-21 2020-04-03 深圳市万普拉斯科技有限公司 视频处理方法、装置、电子设备及存储介质
CN108230255A (zh) * 2017-09-19 2018-06-29 北京市商汤科技开发有限公司 用于实现图像增强的方法、装置和电子设备
CN107590810A (zh) * 2017-09-22 2018-01-16 北京奇虎科技有限公司 实现双重曝光的视频数据处理方法及装置、计算设备
CN108230331A (zh) * 2017-09-30 2018-06-29 深圳市商汤科技有限公司 图像处理方法和装置、电子设备、计算机存储介质
CN108898546B (zh) * 2018-06-15 2022-08-16 北京小米移动软件有限公司 人脸图像处理方法、装置及设备、可读存储介质
US10726584B2 (en) * 2018-11-28 2020-07-28 International Business Machines Corporation Displaying a virtual eye on a wearable device
WO2021061112A1 (fr) 2019-09-25 2021-04-01 Google Llc Commande de gain pour une authentification faciale
CN110868525A (zh) * 2019-11-11 2020-03-06 杭州臻信科技有限公司 一种人脸识别摄像装置、设备及系统
CN113132795A (zh) 2019-12-30 2021-07-16 北京字节跳动网络技术有限公司 图像处理方法及装置
CN112991156A (zh) * 2020-10-16 2021-06-18 陈晶晶 基于大数据和人工智能的指令修正方法
US11574388B2 (en) * 2020-12-29 2023-02-07 Adobe Inc. Automatically correcting eye region artifacts in digital images portraying faces
US11350059B1 (en) * 2021-01-26 2022-05-31 Dell Products, Lp System and method for intelligent appearance monitoring management system for videoconferencing applications
CN112837213A (zh) * 2021-02-07 2021-05-25 北京字跳网络技术有限公司 脸型调整图像生成方法、模型训练方法、装置和设备
CN115629698A (zh) * 2021-07-02 2023-01-20 祖玛视频通讯公司 视频通信系统中的动态弱光调节的方法
CN115631124A (zh) * 2021-07-02 2023-01-20 祖玛视频通讯公司 在视频通信系统中提供视频外观调整的方法
US11995743B2 (en) * 2021-09-21 2024-05-28 Samsung Electronics Co., Ltd. Skin tone protection using a dual-core geometric skin tone model built in device-independent space

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060184800A1 (en) * 2005-02-16 2006-08-17 Outland Research, Llc Method and apparatus for using age and/or gender recognition techniques to customize a user interface
US20120051658A1 (en) * 2010-08-30 2012-03-01 Xin Tong Multi-image face-based image processing
US20120208592A1 (en) * 2010-11-04 2012-08-16 Davis Bruce L Smartphone-Based Methods and Systems
US20120313937A1 (en) * 2010-01-18 2012-12-13 Disney Enterprises, Inc. Coupled reconstruction of hair and skin
US20130321700A1 (en) * 2012-05-31 2013-12-05 Apple Inc. Systems and Methods for Luma Sharpening
US20130322753A1 (en) * 2012-05-31 2013-12-05 Apple Inc. Systems and methods for local tone mapping
US20140063061A1 (en) * 2011-08-26 2014-03-06 Reincloud Corporation Determining a position of an item in a virtual augmented space
US20140085501A1 (en) * 2010-02-26 2014-03-27 Bao Tran Video processing systems and methods
US20140341422A1 (en) * 2013-05-10 2014-11-20 Tencent Technology (Shenzhen) Company Limited Systems and Methods for Facial Property Identification
US20150042664A1 (en) * 2013-08-09 2015-02-12 Nvidia Corporation Scale-up techniques for multi-gpu passthrough
US20160065856A1 (en) * 2014-08-29 2016-03-03 Samsung Electronics Co., Ltd. Photographing method and electronic device
US20170011210A1 (en) * 2014-02-21 2017-01-12 Samsung Electronics Co., Ltd. Electronic device

Family Cites Families (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7082211B2 (en) * 2002-05-31 2006-07-25 Eastman Kodak Company Method and system for enhancing portrait images
CN1993366A (zh) * 2004-06-30 2007-07-04 纳幕尔杜邦公司 利用气体鼓泡进行的醛糖内酯、醛糖二酸内酯和醛糖二酸双内酯的合成
US8174555B2 (en) * 2007-05-30 2012-05-08 Eastman Kodak Company Portable video communication system
US8520089B2 (en) * 2008-07-30 2013-08-27 DigitalOptics Corporation Europe Limited Eye beautification
US9053524B2 (en) * 2008-07-30 2015-06-09 Fotonation Limited Eye beautification under inaccurate localization
JP2010219740A (ja) * 2009-03-16 2010-09-30 Nikon Corp 画像処理装置およびデジタルカメラ
US11232290B2 (en) * 2010-06-07 2022-01-25 Affectiva, Inc. Image analysis using sub-sectional component evaluation to augment classifier usage
US9508119B2 (en) * 2012-07-13 2016-11-29 Blackberry Limited Application of filters requiring face detection in picture editor
US8774519B2 (en) * 2012-08-07 2014-07-08 Apple Inc. Landmark detection in digital images
CN103685926B (zh) * 2012-09-21 2017-05-10 宏达国际电子股份有限公司 面部区域的影像处理方法以及使用此方法的电子装置
WO2014189613A1 (fr) * 2013-05-24 2014-11-27 Intel Corporation Amélioration d'image accordable de carnation
US20140369554A1 (en) * 2013-06-18 2014-12-18 Nvidia Corporation Face beautification system and method of use thereof
US9361510B2 (en) * 2013-12-13 2016-06-07 Intel Corporation Efficient facial landmark tracking using online shape regression method
US10453270B2 (en) * 2015-09-11 2019-10-22 Intel Corporation Scalable real-time face beautification of video images
US20190206031A1 (en) * 2016-05-26 2019-07-04 Seerslab, Inc. Facial Contour Correcting Method and Device
US10621771B2 (en) * 2017-03-21 2020-04-14 The Procter & Gamble Company Methods for age appearance simulation
US10614623B2 (en) * 2017-03-21 2020-04-07 Canfield Scientific, Incorporated Methods and apparatuses for age appearance simulation
EP3890591A4 (fr) * 2018-12-04 2022-08-10 Jiang, Ruowei Diagnostics cutanés automatiques basés sur l'image à l'aide d'un apprentissage profond

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060184800A1 (en) * 2005-02-16 2006-08-17 Outland Research, Llc Method and apparatus for using age and/or gender recognition techniques to customize a user interface
US20120313937A1 (en) * 2010-01-18 2012-12-13 Disney Enterprises, Inc. Coupled reconstruction of hair and skin
US20140085501A1 (en) * 2010-02-26 2014-03-27 Bao Tran Video processing systems and methods
US20120051658A1 (en) * 2010-08-30 2012-03-01 Xin Tong Multi-image face-based image processing
US20120208592A1 (en) * 2010-11-04 2012-08-16 Davis Bruce L Smartphone-Based Methods and Systems
US20140063061A1 (en) * 2011-08-26 2014-03-06 Reincloud Corporation Determining a position of an item in a virtual augmented space
US20130321700A1 (en) * 2012-05-31 2013-12-05 Apple Inc. Systems and Methods for Luma Sharpening
US20130322753A1 (en) * 2012-05-31 2013-12-05 Apple Inc. Systems and methods for local tone mapping
US20140341422A1 (en) * 2013-05-10 2014-11-20 Tencent Technology (Shenzhen) Company Limited Systems and Methods for Facial Property Identification
US20150042664A1 (en) * 2013-08-09 2015-02-12 Nvidia Corporation Scale-up techniques for multi-gpu passthrough
US20170011210A1 (en) * 2014-02-21 2017-01-12 Samsung Electronics Co., Ltd. Electronic device
US20160065856A1 (en) * 2014-08-29 2016-03-03 Samsung Electronics Co., Ltd. Photographing method and electronic device

Also Published As

Publication number Publication date
US11741682B2 (en) 2023-08-29
US20180174370A1 (en) 2018-06-21
US20200151964A1 (en) 2020-05-14
US11328496B2 (en) 2022-05-10
US20220020226A1 (en) 2022-01-20
US20230401807A1 (en) 2023-12-14
WO2017041289A1 (fr) 2017-03-16

Similar Documents

Publication Publication Date Title
US11741682B2 (en) Face augmentation in video
US10152778B2 (en) Real-time face beautification features for video images
US10885384B2 (en) Local tone mapping to reduce bit depth of input images to high-level computer vision tasks
US20140003662A1 (en) Reduced image quality for video data background regions
US9860553B2 (en) Local change detection in video
US10664949B2 (en) Eye contact correction in real time using machine learning
US9342749B2 (en) Hardware convolution pre-filter to accelerate object detection
CN110072033B (zh) 使用选择性色彩变换的色彩压缩
US9600864B2 (en) Skin tone tuned image enhancement
US20160088298A1 (en) Video coding rate control including target bitrate and quality control
US9525803B2 (en) Object detection using motion estimation
US20140002732A1 (en) Method and system for temporal frame interpolation with static regions excluding
WO2022104618A1 (fr) Réseaux de fusion profonds compacts bidirectionnels pour des applications d'analyse visuelle à modalités multiples
WO2022061726A1 (fr) Procédé et système de reconnaissance d'attributs faciaux multiples à l'aide de réseaux neuronaux hautement efficaces
US9019340B2 (en) Content aware selective adjusting of motion estimation
US20170323416A1 (en) Processing image fragments from one frame in separate image processing pipes based on image analysis
US10846142B2 (en) Graphics processor workload acceleration using a command template for batch usage scenarios
US9615104B2 (en) Spatial variant dependency pattern method for GPU based intra prediction in HEVC
US20240107086A1 (en) Multi-layer Foveated Streaming
US20140192071A1 (en) Techniques for improved graphics encoding

Legal Events

Date Code Title Description
STPP Information on status: patent application and granting procedure in general

Free format text: FINAL REJECTION MAILED

STPP Information on status: patent application and granting procedure in general

Free format text: RESPONSE AFTER FINAL ACTION FORWARDED TO EXAMINER

STPP Information on status: patent application and granting procedure in general

Free format text: NOTICE OF ALLOWANCE MAILED -- APPLICATION RECEIVED IN OFFICE OF PUBLICATIONS

AS Assignment

Owner name: INTEL CORPORATION, CALIFORNIA

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:CHEN, KE;DENG, ZHIPIN;CAI, XIAOXIA;AND OTHERS;SIGNING DATES FROM 20190807 TO 20190829;REEL/FRAME:050223/0957

STPP Information on status: patent application and granting procedure in general

Free format text: PUBLICATIONS -- ISSUE FEE PAYMENT RECEIVED

STCF Information on status: patent grant

Free format text: PATENTED CASE

AS Assignment

Owner name: TAHOE RESEARCH, LTD., IRELAND

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:INTEL CORPORATION;REEL/FRAME:061175/0176

Effective date: 20220718

MAFP Maintenance fee payment

Free format text: PAYMENT OF MAINTENANCE FEE, 4TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1551); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

Year of fee payment: 4